The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper describes an approach to automate the detection and classification of tuberculosis (TB) bacilli in tissue section using image processing technique and feedforward neural network trained by Extreme Learning Machine. It aims to assist pathologists in TB diagnosis and give an alternative to the conventional manual screening process, which is time-consuming and labour-intensive. Images are...
Recent evidence in neuroscience support the theory that prediction of spatial and temporal patterns in the brain plays a key role in human actions and perception. Inspired by these findings, a system that discriminates laughter from speech by modeling the spatial and temporal relationship between audio and visual features is presented. The underlying assumption is that this relationship is different...
The choice of optimal topology of neural network (NN) is one of the most important factor for the success of any application. Generally the optimization of neural network (NN) has based on cross validation method which requires more learning and test procedures. This paper proposes the use of sophisticated methods, it is one of the pruning NN methods as: "Optimal Brain Damage" (OBD) and...
This paper investigates the Malay speaker identification using Neural Networks. Speech database was developed with five speakers as trainers and five speakers as imposters. The speech training set included 30 vowel sounds of five trainer speakers. The test set included 30 vowel sounds from the five trainers and 30 vowel sounds from five imposters. The speech sounds were sampled at 20 kHz with 16 bit...
Studies of paleoclimate variations in local regions are seriously restricted by the low resolution and uncertainties of the simulated data at present. In order to apply large-scale modeling data to paleoclimate research in local regions, an effective downscaling model based on three-layer back propagation neural network (BPNN) is developed. Observational and ECHO-G simulated data are employed to train...
For fire detection and alarm system with simple function, positioning difficulties, false positive and false negative in traditional intelligent building, the fire detection and alarm systems based on intelligent neural network have been designed. It can do integrated estimation with a variety of fire detection information detected by the microcontroller, neural network intelligent algorithm was joined...
In the current power and energy scenario, distributed generation (DG) has generated a lot of interest across the globe due to the growing concerns about gradual depletion of fossil fuels, steep load growth, environmental pollution and global warming caused by greenhouse gas emissions. Renewable DGs such as wind generators and solar photovoltaic are well-recognized now-a-days as sources of clean energy...
In the mining industry, knowing the position of miners and/or equipments is an important safety measure that reduces risks and improves the security of that facility. Being an indoor environment, wireless transmitted signals in underground narrow-vein mines suffer multiple kinds of distortions due to extreme multipath and non-line of sight (NLOS) conditions. One of the proposed solutions to accurate...
This paper presents the use of a Wavelet Neural Network (WNN) as an efficient classifier of Electromyographic (EMG) signals. Generally, an EMG signal requires advanced methods for detection, decomposition, processing and classification. In this paper a WNN model will relate the firing frequency of motor unit action potentials (MUAPs) and three different muscle force levels, in order to improve the...
High-throughput microscopy allows fast imaging of large tissue samples, producing an unprecedented amount of sub-cellular information. The size and complexity of these data sets often out-scale current reconstruction algorithms. Overcoming this computational bottleneck requires extensive parallel processing and scalable algorithms. As high-throughput imaging techniques move into main stream research,...
Power utilization has become a major issue in portable designs, since its battery storage is less compared to its usage. One of the popular techniques to solve this problem is to use Dynamic Power Management (DPM) at the system level. Dynamic power management is a technique used to save power when the system is idle. Earlier it was assumed that the prediction can be done only in long range dependent...
The human hand is a complex system, with a large number of degrees of freedom (DoFs), sensors embedded in its structure, actuators and tendons, and a complex hierarchical control. Despite this complexity, the efforts required to the user to carry out the different movements are quite small. On the contrary, prosthetic hands are just a pale replication of the natural hand, with significantly reduced...
A GPU-accelerated OpenCL implementation of a back-propagation artificial neural network for the creation of QSAR models for drug discovery and virtual high-throughput screening is presented. A QSAR model for HSD achieved an enrichment of 5.9 and area under the curve of 0.83 on an independent data set which signifies sufficient predictive ability for virtual high-throughput screening efforts. The speed-up...
In this paper radial basis function neural network (RBFNN) is used to extract total harmonics in converter waveforms. The methodology is based on p-q (real power-imaginary power) theory. The converter waveforms are analyzed and the harmonics over a wide operating range are extracted. The proposed RBFNN filtering training algorithms are based on an efficient training method called hybrid learning method...
We introduce a mobile robotic system able to learn through reinforcement, which allows it to navigate within a dynamic environment (e.g. a room) avoiding any obstacle it might encounter. The robotic system must be able to locate and reach an established pattern, which has been previously learned. The learning system is implemented with two neural networks. Both neural networks use reinforcement learning...
In this paper we present a model of organic TFT based on neural network. This approach allows a fast and easy way to model devices having a strong non-linear behavior, without entering in the device physics. The same network structure can be adapted for different devices after a training stage were the connection weights between the network elements are defined. Results show that few DC measures are...
This paper presents modeling ballistic double gate MOSFETs by a neural network approach. A complete neural network structure is proposed to model the double gate characteristics. To confirm the accuracy of the proposed network, the drain current characteristics are compared to the nanoMOS device simulator data. The comparison shows excellent agreements with percentage errors lower than 1% over a range...
Information acquired from any species genomic sequence is expected to contribute massively to advances in various fields, such as medicine, forensics and agriculture. This huge impact of DNA sequencing leads to the need for efficient automation of mapping chromatogram traces to their corresponding string of bases through base-calling. This paper attempts to solve the problem of base-calling by modeling...
This paper presents the classification of three mental tasks, using the electroencephalographic signal and simulating a real-time process. Three types of classifiers are compared: k-nearest neighbors, Linear Discriminant Analysis and feed-forward backpropagation Artificial Neural Networks. The mental tasks are the imagination of right or left hand movements and generation of words beginning with the...
The paper introduces two neural network techniques to compare and analyze the detection level of Alzheimer's disease in a patient. The proposed module uses a Neurological Memory test named Mini Mental Status Examination (MMSE). It is authorized to be used only by neurologist, neuropsychologist and psychiatrist for determining the cognitive level. Doctors use the score of MMSE to evaluate the cognitive...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.